Loading...
Loading...
Found 55 Skills
Compare Replicate models by cost, speed, quality, and capabilities.
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.
Create validated LLM-as-a-Judge evaluators following best practices — binary Pass/Fail judges with TPR/TNR validation for measuring specific failure modes. Use when you need to automate quality checks, build guardrails, or measure a specific failure mode identified during trace analysis. Do NOT use when failures are fixable with prompt changes (use optimize-prompt) or when failure modes are unknown (use analyze-trace-failures first).
Evaluates ML models for performance, fairness, and reliability. Use for metric selection, cross-validation strategies, overfitting/underfitting diagnosis, hyperparameter tuning, LLM evaluation, A/B testing, and production monitoring for model drift.
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.
Build and run LLM-as-judge evaluation pipelines using Amazon Bedrock Evaluation Jobs with pre-computed inference datasets. Use when setting up automated model evaluation, designing test scenarios, collecting pre-computed responses, configuring custom metrics, creating AWS infrastructure, running evaluation jobs, parsing results, and iterating on findings.
Complete reference for the Galileo AI platform Python SDK for evaluating, observing, and protecting GenAI applications. Use when building Python applications that need LLM evaluation, production observability, tracing, or runtime guardrails with Galileo.
Run cross-framework agent comparisons using evaluatorq from orqkit — compares any combination of agents (orq.ai, LangGraph, CrewAI, OpenAI Agents SDK, Vercel AI SDK) head-to-head on the same dataset with LLM-as-a-judge scoring. Use when comparing agents, benchmarking, or wanting side-by-side evaluation. Do NOT use when comparing only orq.ai configurations with no external agents (use run-experiment instead).
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.